mcp-atlassian is a Model Context Protocol server that lets AI assistants work with Atlassian's Confluence and Jira services. Developers use it to search documentation, find issues, create tickets, and update Jira work through an assistant, with support for Cloud and Server/Data Center deployments. The catalogue entries provide instructions and settings for using the server.
Borrowing it
Nothing to install: this file belongs to sooperset/mcp-atlassian. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sooperset/mcp-atlassian/main/AGENTS.mdgit clone --depth 1 https://github.com/sooperset/mcp-atlassianWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/sooperset/mcp-atlassian/agents-md)<a href="https://agentmods.dev/instructions/sooperset/mcp-atlassian/agents-md"><img src="https://agentmods.dev/badge/instructions/sooperset/mcp-atlassian/agents-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01096 | $0.01096 |
| Opus 5 | $0.00548 | $0.00548 |
| Sonnet 5 | $0.00219 | $0.00219 |
| Haiku 4.5 | $0.00110 | $0.00110 |
Grade A, and why
mcp-atlassian AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
8 near-identical copies found in the catalogue:
- ai_agent_mcp_jira AGENTS.md — 100% identical, 0 lines differ
- AtlMCPforDC AGENTS.md — 100% identical, 0 lines differ
- atlassian-mcp-server AGENTS.md — 100% identical, 0 lines differ
- mcp-atlassian AGENTS.md — 94% identical, 1 lines differ
- mcp-atlassian AGENTS.md — 94% identical, 1 lines differ
- jira-mcp AGENTS.md — 94% identical, 1 lines differ
- mcp-atlassian-with-bitbucket AGENTS.md — 91% identical, 7 lines differ
- mcp-atlassian-dc AGENTS.md — 91% identical, 7 lines differ
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Atlassian
Audience: LLM-driven engineering agents
Repository map
| Path | Purpose |
|---|---|
src/mcp_atlassian/ |
Library source (Python ≥ 3.10) |
├─ jira/ |
Jira client + 21 mixins (issues, search, SLA, metrics, …) |
├─ confluence/ |
Confluence client + 8 mixins (pages, search, analytics, …) |
├─ models/ |
Pydantic v2 data models (ApiModel base) |
├─ servers/ |
FastMCP server instances (jira_mcp, confluence_mcp) |
├─ preprocessing/ |
Content conversion (ADF/Storage → Markdown) |
└─ utils/ |
Shared utilities (auth, logging, SSL, decorators) |
tests/ |
Pytest suite — unit, integration, real-API validation |
scripts/ |
OAuth setup and testing scripts |
Architecture
- Mixin composition:
JiraFetchercomposes 21 mixins,ConfluenceFetchercomposes 8. Client inheritance is transitive through mixins. - FastMCP servers:
servers/main.py→ lifespan → dependency injection viaget_jira_fetcher(ctx)/get_confluence_fetcher(ctx). - Tool naming:
{service}_{action}_{target}(e.g.,jira_create_issue,confluence_get_page). - Config: Environment-based
from_env()factory onJiraConfig/ConfluenceConfigdataclasses. - Auth: Basic (Cloud + Server/DC), PAT (Server/DC), OAuth 2.0 (Cloud + Server/DC) — with multi-tenant header support.
- Models: All extend
ApiModel→from_api_response()+to_simplified_dict().
Dev workflow
uv sync --frozen --all-extras --dev # install dependencies
pre-commit install # setup hooks
pre-commit run --all-files # Ruff + mypy
uv run pytest -xvs # full test suite
uv run pytest tests/unit/ -xvs # unit tests only
uv run pytest tests/integration/ # integration tests
uv run pytest --cov=src/mcp_atlassian --cov-report=term-missing # coverage
Tests must pass and lint/typing must be clean before committing.
Rules
- Package management: ONLY use
uv, NEVERpip - Branching: NEVER work on
main, always create feature branches - Type safety: All functions require type hints
- Testing: New features need tests, bug fixes need regression tests
- Commits: Use trailers for attribution, never mention tools/AI
- Commit types:
feat,fix,docs,refactor,test,chore,perf,ci— scopes:jira,confluence,server,auth,docker,docs - File hygiene: Prefer editing existing files over creating new ones
- Tool docs: After changing tool signatures or registrations, run
uv run python scripts/generate_tool_docs.pyand commit the diff; CI (Docs / check) enforces this
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 98 lines · 1,096 tokens per session scan A aa9ab6cc3cb4
mcp-atlassian AGENTS.md is an instructions file published in the GitHub repository sooperset/mcp-atlassian (5,853 stars, last pushed yesterday), licensed MIT. It adds 1,096 tokens to every session, about $0.0055 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.